Skip to content

Commit

Permalink
Add changelog and update readme
Browse files Browse the repository at this point in the history
  • Loading branch information
ajtudela committed Sep 21, 2021
1 parent f044075 commit 97c60b5
Show file tree
Hide file tree
Showing 3 changed files with 39 additions and 3 deletions.
30 changes: 30 additions & 0 deletions CHANGELOG.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Changelog for package object_detection_openvino
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2.0.0 (13-09-2021)
------------------
* Create CHANGELOG.rst.
* Fix camera info in depth analysis.

1.6.0 (09-07-2021)
------------------
* Added nodelet option for vision pipeline.

1.5.0 (25-06-2021)
------------------
* Change to OpenVino 2020.3.355.
* Remove custom messages and replaces them by vision_msgs.

1.1.0 (21-10-2020)
------------------
* Update OpenVino version to 2020.3

1.0.0 (25-09-2020)
------------------
* Initial release.
* Create README.md.
* Added objectDetectionOpenvino class (.h and .cpp files).
* Added BoundingBox.msg, BoundingBox3d.msg, BoundingBox3dArray.msg and BoundingBoxArray.msg messages.
* Added launch files.
* Added initial YOLO and mobilenet-ssd models.
* Contributors: Alberto Tudela
10 changes: 8 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,12 +1,16 @@
# object_detection_openvino

![ROS](https://img.shields.io/badge/ros-melodic-blue?style=for-the-badge&logo=ros&logoColor=white)
![OpenCV](https://img.shields.io/badge/opencv-%23white.svg?style=for-the-badge&logo=opencv&logoColor=white)
![License](https://img.shields.io/badge/license-Apache%202-blue?style=for-the-badge)

## Overview

An implementation of YOLO and Mobilenet-SSD object detection with a ROS interface and enhanced processor utilization using OpenVINO model optimization tools. It can be use with any Myriad X, i.e.: Intel Neural Compute Stick 2.
This package is designed on async api of [Intel OpenVINO](https://software.intel.com/en-us/openvino-toolkit) and allows an easy setup for **object detection**.<br><br>
If you provide a depth image (from an Intel RealSense Camera, for example) you can obtain 3d boxes and markers in [RViz].

**Keywords:** ROS, OpenVino, RealSense, object_detection
**Keywords:** ROS, OpenVino, RealSense, OpenCV, object_detection

### License

Expand All @@ -23,7 +27,9 @@ The object_detection_openvino package has been tested under [ROS] Melodic on [Ub
#### Dependencies

- [Robot Operating System (ROS)](http://wiki.ros.org) (middleware for robotics),
- [Intel OpenVINO 2020.3.355](https://software.intel.com/en-us/openvino-toolkit)
- [Intel OpenVINO 2020.3.355](https://software.intel.com/en-us/openvino-toolkit) (toolkit for deep learning),
- [OpenCV 3](https://opencv.org/) (Computer Vision library),
- [Boost](https://www.boost.org/) (C++ source libraries)

sudo rosdep install --from-paths src

Expand Down
2 changes: 1 addition & 1 deletion package.xml
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
<?xml version="1.0"?>
<package format="2">
<name>object_detection_openvino</name>
<version>1.0.0</version>
<version>2.0.0</version>
<description>OpenVINO implementation of Darknet ROS (YoloV3) and Mobilenet-SSD networks to achieve realtime processing on x64 CPUs.</description>
<maintainer email="[email protected]">Alberto Tudela</maintainer>
<author email="[email protected]">Alberto Tudela</author>
Expand Down

0 comments on commit 97c60b5

Please sign in to comment.